e499de7486
后端 - check 模块：检查预览、发起、进度、取消、记录；六个阶段（准备投标文件、响应匹配、规则、证据校验、 状态沿用、汇总）；问题列表、处理、撤销、批量处理（只限提示级）。 - 每条清单项的检查结论 check_item_result（C9，迁移 0005）：「已响应」也带投标原文出处； 没有校验通过的证据不能判已响应（C3）。级别从清单项算，不让模型定；说明不写整改建议。 - 响应匹配先只有第三层：内存 BM25 检索候选句 + check.match v1 提示词，检索不到不调模型， 漏答记 missing_answer，模型临时错误只影响那一批。 - 计费：免费版不记流水；专业版 24 小时内复查免扣（记一行 0）；expected_charge 不一致时拒绝不扣点； 失败、取消退回；投标文件读不出文字按输入问题失败、不扣点。 - 投标分册：类型（volume_kind）和版本；电子投标平台加密格式在上传时拦下。 - 解析流水线前几个阶段拆到 document/pipeline/normalize.py，解析和检查共用。 - ops 模块：反馈接口；致命问题确认无误的说明自动进误报反馈（U4）。 - SK1：Valkey 客户端短超时、SSE 连接池上限。SK2：CI 加 Gotenberg、直接跑 init-roles.sh。 前端 - 上传投标文件并检查页、查标页（进度、覆盖范围、按级别筛选、逐条处理和行内说明、撤销、原文抽屉、 已处理、本次已解决）；项目头抽成公共组件，加「查标」标签页；工作台「下一步」覆盖查标阶段。 契约、文档：openapi.yaml 加 item-results、volume_kind、coverage 字段；data-model、api-design §10、 架构 §8 / §13（SK14）、AGENTS.md 同步。 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
80 lines
3.9 KiB
Python
80 lines
3.9 KiB
Python
"""查标的纯函数：检索、投标侧证据校验、问题级别（m3-plan §2）。"""
|
||
|
||
from __future__ import annotations
|
||
|
||
from uuid import uuid4
|
||
|
||
from bid_doctor.check import findings, match
|
||
from bid_doctor.check.retrieval import Index, tokens
|
||
from bid_doctor.document.pipeline.text_layer import Sentence
|
||
|
||
|
||
def sent(seq: int, text: str, page: int = 1) -> Sentence:
|
||
return Sentence(key=f"doc:p{page}:s{seq}", page_no=page, seq=seq, text=text, quads=[[0, 0, 1, 1]])
|
||
|
||
|
||
def test_tokens_keep_number_unit_and_model_names() -> None:
|
||
t = tokens("服务器内存不低于32GB，支持10GE和硬件BFD")
|
||
assert "32gb" in t and "10ge" in t and "bfd" in t and "内存" in t
|
||
|
||
|
||
def test_bm25_ranks_the_responding_sentence_first() -> None:
|
||
index = Index(
|
||
[
|
||
sent(1, "我公司提供7×24小时售后服务。"),
|
||
sent(2, "服务器内存配置为64GB，并提供产品彩页。"),
|
||
sent(3, "交换机支持硬件BFD，最小发送间隔3.3毫秒。"),
|
||
]
|
||
)
|
||
(top, *_) = index.search("交换机支持硬件BFD 最小报文发送间隔不大于50毫秒", 3)
|
||
assert top.sentence.seq == 3
|
||
assert index.search("完全无关的词语组合", 3) == []
|
||
|
||
|
||
def bid() -> tuple[match.BidDoc, dict[str, tuple[match.BidDoc, Sentence]]]:
|
||
s = sent(9, "服务器内存不低于32GB的要求：我方服务器内存配置为64GB。")
|
||
d = match.BidDoc(uuid4(), 1, "技术分册", [s])
|
||
return d, {"d1p1s9": (d, s)}
|
||
|
||
|
||
def test_responded_needs_verified_evidence() -> None:
|
||
"""模型说已响应，但证据没通过：不能判已响应，记「未找到响应」并带原因码（C3）。"""
|
||
_, allowed = bid()
|
||
ok = match.judge(
|
||
{"verdict": "responded", "evidence": [{"sid": "d1p1s9", "quote": "我方服务器内存配置为64GB。"}]}, allowed, []
|
||
)
|
||
assert ok.verdict == "responded" and ok.evidence_status == "verified" and len(ok.evidence) == 1
|
||
|
||
no_ev = match.judge({"verdict": "responded", "evidence": []}, allowed, [])
|
||
assert (no_ev.verdict, no_ev.evidence_status, no_ev.reason_code) == ("not_found", "unverified", "evidence_missing")
|
||
|
||
rewritten = match.judge(
|
||
{"verdict": "responded", "evidence": [{"sid": "d1p1s9", "quote": "内存为64GB，满足要求。"}]}, allowed, []
|
||
)
|
||
assert rewritten.reason_code == "quote_not_original" and rewritten.detail["claimed_pages"] == [1]
|
||
|
||
other = match.judge({"verdict": "responded", "evidence": [{"sid": "d1p2s1", "quote": "x" * 10}]}, allowed, [])
|
||
assert other.reason_code == "sid_unknown"
|
||
|
||
missing = match.judge(None, allowed, ["技术分册"])
|
||
assert (missing.verdict, missing.reason_code) == ("undetermined", "missing_answer")
|
||
|
||
|
||
def test_severity_comes_from_the_item_not_the_model() -> None:
|
||
assert findings.severity({"importance": "substantive", "categories": ["tech_param", "invalidity"]}) == "fatal"
|
||
assert findings.severity({"importance": "normal", "categories": ["qualification"]}) == "fatal"
|
||
assert findings.severity({"importance": "important", "categories": ["tech_param"]}) == "important"
|
||
assert findings.severity({"importance": "normal", "categories": ["scoring"]}) == "important"
|
||
assert findings.severity({"importance": "normal", "categories": ["tech_param"]}) == "hint"
|
||
|
||
|
||
def test_no_value_is_a_hint_and_unverified_is_explained() -> None:
|
||
item = {"title": "服务器内存", "importance": "substantive", "categories": ["tech_param"]}
|
||
nv = findings.spec(match.Result("no_value", "model", "verified"), item)
|
||
assert nv is not None and nv.severity == "hint" and nv.title.startswith("未给出具体值")
|
||
uv = findings.spec(
|
||
match.Result("not_found", "model", "unverified", "quote_not_original", detail={"claimed_pages": [3]}), item
|
||
)
|
||
assert uv is not None and uv.severity == "fatal" and "第 3 页" in uv.explanation and "没能核对" in uv.explanation
|
||
assert findings.spec(match.Result("responded", "model", "verified"), item) is None
|